The majority of surface irrigation schemes are diverse in character, consisting of a diversity of crops and soils as well as a huge network of canals with varying qualities (design capacities, efficiencies, command area, length, duration of operation, etc.). The programs in semiarid and arid locations are similarly related to limited water supplies and operate on a rotating water distribution system. As a result, managing irrigation in such settings is tough. It demands decisions on how much water and space should be allotted to different crops grown on different soils and in different areas or regions of the scheme (the allocation plan), based on water availability, benefit maximization, varied needs, and the physical boundaries of the scheme. The current study focuses on the use of Genetic Algorithms (GA) to irrigation planning. In India, the GA technique is being used to create an effective farming plan for an irrigation project. Constraints include land and water limitations, as well as crop and storage limits. The model is run for various choices of population, generations, cross over, and mutation probabilities to determine GA parameters. The results of GA are compared to those of Linear Programming. This case study is about a problem with linear constraints that was addressed using a genetic algorithm. The model's future use will be to address issues with non-linear constraints. Traditional nonlinear programming approaches become difficult and time intensive in such instances. Future research is being conducted to improve the efficiency and usability of these artificial intelligence systems.